Improving Compression Based Dissimilarity Measure for Music Score Analysis

TL;DR

This paper enhances the compression-based dissimilarity measure (CDM) for music score analysis by modifying file size calculations, leading to more accurate composer classification of piano pieces.

Contribution

It introduces a modified CDM that improves dissimilarity measurement accuracy specifically for music score analysis.

Findings

Modified CDM improves composer classification accuracy

Results are statistically significant

Enhanced measure outperforms original CDM in experiments

Abstract

In this paper, we propose a way to improve the compression based dissimilarity measure, CDM. We propose to use a modified value of the file size, where the original CDM uses an unmodified file size. Our application is a music score analysis. We have chosen piano pieces from five different composers. We have selected 75 famous pieces (15 pieces for each composer). We computed the distances among all pieces by using the modified CDM. We use the K-nearest neighbor method when we estimate the composer of each piece of music. The modified CDM shows improved accuracy. The difference is statistically significant.